A Novel Hybrid Model (EMD-TI-LSTM) for Enhanced Financial Forecasting with Machine Learning DOI Creative Commons

Olcay Ozupek,

Reyat Yılmaz, Bita Ghasemkhani

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(17), P. 2794 - 2794

Published: Sept. 9, 2024

Financial forecasting involves predicting the future financial states and performance of companies investors. Recent technological advancements have demonstrated that machine learning-based models can outperform traditional techniques. In particular, hybrid approaches integrate diverse methods to leverage their strengths yielded superior results in prediction. This study introduces a novel model, entitled EMD-TI-LSTM, consisting empirical mode decomposition (EMD), technical indicators (TI), long short-term memory (LSTM). The proposed model delivered more accurate predictions than those generated by conventional LSTM approach on same well-known datasets, achieving average enhancements 39.56%, 36.86%, 39.90% based MAPE, RMSE, MAE metrics, respectively. Furthermore, show has lower MAPE rate 42.91% compared its state-of-the-art counterparts. These findings highlight potential mathematical innovations advance field forecasting.

Language: Английский

The use of artificial intelligence in psychotherapy: development of intelligent therapeutic systems DOI Creative Commons
Liana Spytska

BMC Psychology, Journal Year: 2025, Volume and Issue: 13(1)

Published: Feb. 28, 2025

The increasing demand for psychotherapy and limited access to specialists underscore the potential of artificial intelligence (AI) in mental health care. This study evaluates effectiveness AI-powered Friend chatbot providing psychological support during crisis situations, compared traditional psychotherapy. A randomized controlled trial was conducted with 104 women diagnosed anxiety disorders active war zones. Participants were randomly assigned two groups: experimental group used daily support, while control received 60-minute sessions three times a week. Anxiety levels assessed using Hamilton Rating Scale Beck Inventory. T-tests analyze results. Both groups showed significant reductions levels. receiving therapy had 45% reduction on scale 50% scale, 30% 35% group. While provided accessible, immediate proved more effective due emotional depth adaptability by human therapists. particularly beneficial settings where therapists limited, proving its value scalability availability. However, engagement notably lower in-person therapy. offers scalable, cost-effective solution situations may not be accessible. Although remains reducing anxiety, hybrid model combining AI interaction could optimize care, especially underserved areas or emergencies. Further research is needed improve AI's responsiveness adaptability.

Language: Английский

Citations

2
Perspectives on AI and Novel Technologies Among Older Adults, Clinicians, Payers, Investors, and Developers DOI Creative Commons
Nancy L. Schoenborn, Kacey Chae,

Jacqueline Massare

et al.

JAMA Network Open, Journal Year: 2025, Volume and Issue: 8(4), P. e253316 - e253316

Published: April 4, 2025

Importance Artificial intelligence (AI) and novel technologies, such as remote sensors, robotics, decision support algorithms, offer the potential for improving health well-being of older adults, but priorities key partners across technology innovation continuum are not well understood. Objective To examine suggested applications AI technologies adults among partners. Design, Setting, Participants This qualitative study comprised individual interviews using grounded theory conducted from May 24, 2023, to January 2024. Recruitment occurred via referrals through Johns Hopkins Intelligence Technology Collaboratory Aging Research. included aged 60 years or their caregivers, clinicians, leaders in systems insurance plans (ie, payers), investors, developers. Main Outcomes Measures assess priority areas, payers were asked about most important challenges faced by investors developers opportunities associated with technology. All participants suggestions regarding applications. Payers, end user engagement, all groups except development. Interviews analyzed thematic analysis. Distinct areas identified, frequency type compared participant extent overlap groups. Results 15 caregivers (mean age, 71.3 [range, 65-93 years]; 4 men [26.7%]), clinicians 50.3 33-69 8 [53.3%]), 51.6 36-65 5 [62.5%]), 42.4 31-56 [100%]), 6 42.0 27-62 [100%]). There different partners, between least applications, reminders motivating self-care social engagement. few no that addressed activities daily living, which was frequently reported caregivers. Although agreed on importance engaging users, engagement regulatory barriers stronger influence relative other users. Conclusions Relevance interview found differences Public health, regulatory, advocacy strategies needed raise awareness these priorities, foster align incentives effectively use improve adults.

Language: Английский

Citations

1
Artificial Intelligence in Healthcare: Current Trends and Future Directions DOI Creative Commons
Shambo Samrat Samajdar,

Rupak Chatterjee,

Shatavisa Mukherjee

et al.

Current Medical Issues, Journal Year: 2025, Volume and Issue: 23(1), P. 53 - 60

Published: Jan. 1, 2025

Abstract Artificial intelligence (AI) is a milestone technological advancement that enables computers and machines to simulate human problem-solving capabilities. This article serves give broad overview of the application AI in medicine including current applications future. shows promise changing field medical practice although its practical implications are still their infancy need further exploration. However, not without limitations this also tries address them along with suggesting solutions by which can advance healthcare for betterment mass benefit.

Language: Английский

Citations

0
Generative AI for Dementia Care: Feasibility of AI-Powered Task Verification and Caregiver Support (Preprint) DOI

Joy Lai,

David Black,

K B Beaton

et al.

Published: March 20, 2025

BACKGROUND Caregivers of people living with dementia (PLwD) face significant stress, particularly when verifying whether tasks are truly completed, despite the use digital reminder systems. While PlwD may acknowledge reminders, caregivers often lack a reliable way to confirm task adherence. Generative AI, such as GPT-4, offers potential solution by automating verification through follow-up questioning and supporting caregiver decision-making. OBJECTIVE This feasibility study evaluates an AI-powered system integrated framework for PLwD. Specifically, it examines (1) effectiveness GPT-4 in generating high-quality questions that help verify were actually (2) accuracy AI-driven response flagging mechanism identifying requiring intervention, (3) role feedback refining adaptability. METHODS A theoretical pipeline was designed enhance reminders tailored questions, analyzing responses, categorizing concerns. Each question corresponded specific sent system, aiming assess genuinely completed. To test its feasibility, simulated implemented using anonymized dataset 64 reminders. generated without additional contextual information about PLwD routines. classification flagged completion High, Medium, or Low concern, based on clarity urgency. Simulated incorporated refine quality improve adaptability over time. RESULTS Contextual significantly improved clarity, specificity, relevance AI-generated questions. The demonstrated high accuracy, critical safety-related However, subjective non-urgent posed challenges. Caregiver input iteratively enhanced performance, ensuring balance between automation human oversight. CONCLUSIONS demonstrates integrating generative AI into care support. provide structured completed after acknowledged. findings suggest context-aware prompts, combined iterative feedback, reduce Future research should focus real-world implementation, longitudinal usability, scalability optimize interventions.

Language: Английский

Citations

0
Advances in AI Technology in Healthcare DOI Creative Commons

Mohamed Shehata,

Mostafa A. Elhosseini

Bioengineering, Journal Year: 2025, Volume and Issue: 12(5), P. 506 - 506

Published: May 11, 2025

This Special Issue unites 11 innovative research papers that study artificial intelligence applications in the fields of bioengineering and healthcare [...]

Language: Английский

Citations

0
A mini review of transforming dementia care in China with data-driven insights: overcoming diagnostic and time-delayed barriers DOI Creative Commons
Lu Pan, Xiaolu Lin, Xiaofeng Liu

et al.

Frontiers in Aging Neuroscience, Journal Year: 2025, Volume and Issue: 17

Published: March 3, 2025

Introduction Inadequate primary care infrastructure and training in China misconceptions about aging lead to high mis−/under-diagnoses serious time delays for dementia patients, imposing significant burdens on family members medical carers. Main body A flowchart integrating rural urban areas of pathway is proposed, especially spotting the obstacles mis/under-diagnoses that can be alleviated by data-driven computational strategies. Artificial intelligence (AI) machine learning models built data are succinctly reviewed terms roadmap from home, community hospital settings. Challenges corresponding recommendations clinical transformation then reported viewpoint diverse integrity accessibility, as well models’ interpretability, reliability, transparency. Discussion Dementia cohort study along with developing a center-crossed platform should strongly encouraged, also publicly accessible where appropriate. Only doing so challenges overcome AI-enabled research enhanced, leading an optimized China. Future policy-guided cooperation between researchers multi-stakeholders urgently called 4E (early-screening, early-assessment, early-diagnosis, early-intervention).

Language: Английский

Citations

0
A Novel Hybrid Model (EMD-TI-LSTM) for Enhanced Financial Forecasting with Machine Learning DOI Creative Commons

Olcay Ozupek,

Reyat Yılmaz, Bita Ghasemkhani

et al.

Mathematics, Journal Year: 2024, Volume and Issue: 12(17), P. 2794 - 2794

Published: Sept. 9, 2024

Financial forecasting involves predicting the future financial states and performance of companies investors. Recent technological advancements have demonstrated that machine learning-based models can outperform traditional techniques. In particular, hybrid approaches integrate diverse methods to leverage their strengths yielded superior results in prediction. This study introduces a novel model, entitled EMD-TI-LSTM, consisting empirical mode decomposition (EMD), technical indicators (TI), long short-term memory (LSTM). The proposed model delivered more accurate predictions than those generated by conventional LSTM approach on same well-known datasets, achieving average enhancements 39.56%, 36.86%, 39.90% based MAPE, RMSE, MAE metrics, respectively. Furthermore, show has lower MAPE rate 42.91% compared its state-of-the-art counterparts. These findings highlight potential mathematical innovations advance field forecasting.

Language: Английский

Citations

1